This repository provides reference OpenAPI Tool Server implementations, making it easy and secure for developers to integrate external tooling and data sources into LLM agents and workflows.
- Filesystem Access (servers/filesystem) - Manage local file operations safely with configurable restrictions.
- Git Server (servers/git) - Expose Git repositories for searching, reading, and possibly writing via controlled API endpoints.
- WIP: Database Server (servers/database) - Query and inspect database schemas across common DB engines like PostgreSQL, MySQL, and SQLite.
- Memory & Knowledge Graph (servers/memory) - Persistent memory management and semantic knowledge querying using popular and reliable storage techniques.
- WIP: Web Search & Fetch (servers/web-search) - Retrieve and convert web-based content securely into structured API results usable by LLMs.
Articles on Large Language Models, including RAG, Jupyter integration, complexity and pricing, and more.
Articles on logging, tracing, and observability including Echopraxia, Blindsight, structured log analysis, and more.
A technical blog post about setting up JupyterLab and integrating it with OpenWebUI's code interpreter feature, enabling the LLM to execute and generate code for tasks such as exploratory data analysis.
A user is asking about the compatibility of different modules (GPS, GPIO, I2C, 'Port C' UART) with the Cardputer, specifically whether modules using 'Port C' can be used.
A curated list of resources for the M5Stack Cardputer, a $30 credit-card sized mini computer based on the ESP32-S3. Includes specs, pre-installed apps, community apps, and resources.
The Cardputer v1.1 is a high-performance card computer for engineers featuring the StampS3A microcontroller, 56-key keyboard, 1.14-inch TFT screen, and various connectivity options for prototyping, industrial control, and IoT projects.
The M5Stack Cardputer v1.1 is a high-performance card computer featuring a StampS3A microcontroller, 56-key keyboard, 1.14-inch TFT screen, and various interfaces for expansion and control. It's ideal for rapid prototyping, industrial control, and IoT projects.
A reference manual for the extensible, customizable, self-documenting real-time display editor. This manual corresponds to EMACS version 162.
This article details a method for training large language models (LLMs) for code generation using a secure, local WebAssembly-based code interpreter and reinforcement learning with Group Relative Policy Optimization (GRPO). It covers the setup, training process, evaluation, and potential next steps.
